'seq': seq[ length-orf_start : i + 3 ]} )
return orf_list
# Execute when run as a script
if __name__ == '__main__':
if (len(sys.argv) < 2):
print "Usage: python", sys.argv[0], "<filename in FASTA format> [<min ORF length>]"
else:
fileName = sys.argv[1]
if (len(sys.argv) > 2): # 2nd arg should be an integer
try:
minlen = int(sys.argv[2]) # Convert string to integer
except ValueError: # try-except catches errors
print "\n\tExpecting an integer to define min ORF length, found",
print sys.argv[2]
exit()
else:
minlen = MIN_ORF_LENGTH
print "ORF must be at least", minlen, "Base pairs long"
text = cs190FileUtil.readFastaFile(fileName)
# Time to start finding ORFs!
orf_list = find_all_orfs(text, minlen)
for orf in orf_list:
print "Frame {frame} Start {start} End {end} Len {length}".format(
frame=orf['frame'],start=orf['start'],end=orf['end'],length=orf['length'])
# Take a string and find matches in a Fasta file
# This can be useful when validating other tools
# Search is not case sensitive
#
# Usage:
# python search.py <file> <pattern>
#
# Pattern can be in quotes, or a single string
#
# python search.py EColiK12.fasta "atggttaaag tttatgcccc"
# python search.py EColiK12.fasta atggttaaagtttatgcccc
import string
import sys
import cs190FileUtil # Utility to read Fasta files
if (len(sys.argv) < 3):
print "Usage: python", sys.argv[0], "<filename> <pattern>"
else:
text = cs190FileUtil.readFastaFile(sys.argv[1])
pattern = sys.argv[2]
pattern = cs190FileUtil.prepare(pattern) # Remove any blanks
print "Search for", pattern
# Look for start
for pos in xrange(len(text)):
if (pattern == text[pos:pos+len(pattern)]):
# Print positions starting with 1
print "Start:", pos+1
def findLongestRepeat(text):
max = 1 # Our current goal
maxPos = -1
maxDup = -1
# Start at the begining, and continue for each spot
for pos in range(len(text)):
# Look for a match to the string we are sitting on
dup = text.find(text[pos:pos + max], pos + 1, len(text))
# We have a match: can we extend it?
while (dup > 0):
maxPos = pos
maxDup = dup
max = max + 1 # Now look for a longer match
# Can we find a longer match?
dup = text.find(text[pos:pos + max], dup, len(text))
return [maxPos, maxDup, max - 1]
if (len(sys.argv) != 2):
print("Usage: python", sys.argv[0], "<filename>")
else:
text = cs190FileUtil.readFastaFile(sys.argv[1])
[pos, dup, ln] = findLongestRepeat(text)
print("Found duplicate of length", ln)
print(pos, text[pos:pos + ln])
print(dup, text[dup:dup + ln])
